Can I Run Command R Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 4 kwietnia 2024

Yes

Yes — Command R (35B) at Q3_K_M needs about 26.5 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) (~5.5 GB spare), at ~57.7 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: high · Recommended quantization: Q3_K_M · Estimated speed: ~57.7 tok/s

See what else this hardware can run →

Uruchom w chmurze NVIDIA A40 w RunPod — od $0.44/godz. · stawka sprawdzona 2026-08

lub porównaj w Vast.ai

Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.

RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models	32 GB
Memory bandwidth	1792 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Command R Family on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	81.5 GB	✗ No	—	—	70 GB
Q8_0	48.7 GB	✗ No	—	—	37.2 GB
Q6_K	40.2 GB	✗ No	—	—	28.7 GB
Q5_K_M	36.3 GB	✗ No	—	—	24.8 GB
Q4_K_M	32.7 GB	✗ No	—	—	21.1 GB
Q3_K_M	26.5 GB	✓ Yes	8K	~57.7 tok/s	14.9 GB
Q2_K	23 GB	✓ Yes	8K	~67.6 tok/s	11.5 GB

Newer alternative. Cohere has not released a newer model in this library. If you are choosing today, Mistral Small 4 is a comparable current option. Mistral Small 4 needs at least 75.5 GB at Q4_K_M with an 8K context, so it does not fit the RTX 5090 Desktop (32 GB VRAM, 64 GB RAM).

Which Command R Family sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Command R+ (104B)	65.7 GB	✗ Too large	—
Command R (35B)	32.7 GB	✗ Too large	—

What to watch out for

Q3_K_M is the only quantization that fits, and it is a heavily degraded one — expect noticeably worse output than the same model at Q4_K_M. A smaller model at Q4 is usually the better trade.
2 larger variants of Command R Family do not fit and would need CPU offload or different hardware.

RTX 5090 desktop limitations

575 W board power — budget for a 1000 W+ PSU and the heat it puts into the room.
Models larger than 32 GB must offload to system RAM, which costs roughly an order of magnitude in speed.

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
32 GB of VRAM on the NVIDIA GeForce RTX 5090 at 1792 GB/s.
64 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is computed from this model's published attention configuration.

FAQ